ahrefs
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines templates for executing curl commands that incorporate user-provided domains, URLs, and keywords. This pattern creates a surface for indirect prompt injection or command injection if the agent does not properly sanitize the input before execution. 1. Ingestion points: target-domain, target-url, and keyword placeholders in SKILL.md. 2. Boundary markers: Not present in the command templates. 3. Capability inventory: Network requests via curl and file writing to /tmp/ahrefs_request.json. 4. Sanitization: No input validation or escaping logic is specified within the skill instructions.
Audit Metadata